In recent years, recommendation systems have evolved to consider not only accuracy but also diversity and novelty when recommending item lists to users. Existing diversity models primarily focus on recommending the most diverse item lists to all users. However, not every user requires the maximum level of diversity in their recommendations. To address this, this paper proposes a PRDG (Personalized Recommendation with Diversified Graph Neural Networks based Recommender System) for recommendation. Unlike traditional single recommendation models, PRDG includes two advisors—one relevance-oriented and the other diversity-oriented. First, a user’s diversity scoring method is introduced to classify users. Then, different recommendation strategies are applied to different user to achieve personalized recommendations. Lastly, personalized negative sampling modules and re-ranking modules are proposed to enhance recommendation diversity and alleviate popularity bias. To validate the accuracy and diversity of the model, experiments are conducted on the Amazon-Beauty, Amazon-Music, and TaoBao datasets. The experimental results demonstrate that the proposed model significantly improves recommendation accuracy while maintaining comparable diversity to state-of-theart baselines.

Multi-hop Question Answering using the knowledge graph (KG) as a data source requires subject entities and relations that are obtained from natural language questions; the answers are then obtained by reasoning through multiple triples in the KG. However, even large KGs are incomplete, and the reasoning often fails to obtain the correct answer due to the lack of relations in the KG. Recently, researchers have proposed introducing KG embedding into the multi-hop knowledge graph question answering (KGQA) field to solve the incompleteness of the KG. However, these methods embed the question and the KG into different semantic spaces, and it is difficult to obtain the correct answers. Furthermore, due to the limitation of the question embedding sequence, the contribution of each word to the question semantics cannot be distinguished. To overcome the above problems, this paper proposes an effective multi-hop KGQA model, TIPNet, using relation embeddings in knowledge graph triples, which uses the idea of translation models to narrow the semantic spatial distance between question embeddings and KG embeddings. At the same time, TIP weighting technology is proposed to distinguish the semantic contribution of words to the question. To validate the performance of TIPNet, experiments were conducted on the WebQSP and CWQ datasets, and the model reached advanced levels under both KG-full and KG-half settings.

Social media analytics has drawn new quantitative insights of human activity patterns. Many applications of social media analytics, from pandemic prediction to earthquake response, require an in-depth understanding of how these patterns change when human encounter unfamiliar conditions. In this paper, we select two earthquakes in China as the social context in Sina-Weibo (or Weibo for short), the largest Chinese microblog site. After proposing a formalized Weibo information flow model to represent the information spread on Weibo, we study the information spread from three main perspectives: individual characteristics, the types of social relationships between interactive participants, and the topology of real interaction networks. The quantitative analyses draw the following conclusions. First, the shadow of Dunbar's number is evident in the "declared friends/followers" distributions, and the number of each participant's friends/followers who also participated in the earthquake information dissemination show the typical power-law distribution, indicating a rich-gets-richer phenomenon. Second, an individual's number of followers is the most critical factor in user influence. Strangers are very important forces for disseminating real-time news after an earthquake. Third, two types of real interaction networks share the scale-free and small-world property, but with a looser organizational structure. In addition, correlations between different influence groups indicate that when compared with other online social media, the discussion on Weibo is mainly dominated and influenced by verified users.

CPNs has been a useful tool not only to approximate a discrete system but also to model a continuous process. In this paper, CPNs are augmented with maximal and minimal firing speeds, and Interval speed CPNs (ICPNs) is defined. The enabling and firing of transitions of ICPNs are discussed, and the enabling of continuous transitions is classified into three levels: 0-level, 1-level and 2-level. Some rules to calculate the instantaneous firing speeds are also developed. In addition, illustrative examples are presented.